IDSS Distinguished Seminar Series Sanjeev Arora
A Theory for Representation Learning via Contrastive Objectives
Abstract: Representation learning seeks to represent complicated data (images, text etc.) using a vector embedding, which can then be used to solve complicated new classification tasks using simple methods like a linear classifier. Learning such embeddings is an important type of unsupervised learning (learning from unlabeled data) today. Several recent methods leverage pairs of "semantically…